Lightricks: ltx-2-pro
1 benchmarks
Leaderboard position
#841
Overall rank (of 1121 models)
375
Elo rating
1
Benchmarks
Top 75.0%
Percentile
In Lightricks (of 2 models)
Above: perplexity: r1-1776 #840
Below: OpenAI: whisper-large-v3 #842
Benchmark highlights
Nearest competitor from another company
The model from another company with the most similar benchmark scores.
appeared as nearest in 1 of 1 benchmarks
1/1
100.0%
Benchmarks
Predicted scores
Estimated from 25 similar models and the global Elo rating. These are projections, not measured results.
| Benchmark | Predicted | Confidence | Based on |
|---|---|---|---|
| MATH-500 | ~78.07 | 50% | — |
| AIME 2025 | ~50.37 | 50% | — |
| AIME 2026 | ~64.22 | 50% | — |
| HMMT Feb 2026 | ~55.7 | 50% | — |
| GPQA Diamond | ~47.54 | 50% | — |
| MMLU-Pro | ~49.46 | 50% | — |
| Humanity's Last Exam (no tools) | ~4 | 50% | — |
| IFEval | ~75.72 | 50% | — |
| IFBench | ~45.4 | 50% | — |
| HumanEval | ~59.79 | 50% | — |
| MBPP | ~58.8 | 50% | — |
| Terminal-Bench v2.1 | ~8.6 | 50% | — |
| MMLU | ~55.32 | 50% | — |
| SWE-bench Verified | ~24.15 | 50% | — |
| SWE-bench Pro | ~5.24 | 50% | — |
| SciCode | ~19.43 | 50% | — |
| AA-LCR | ~33.73 | 50% | — |
| Artificial Analysis Intelligence Index v5.0.1 | ~12 | 50% | — |
| Humanity's Last Exam (with tools) | ~11.9 | 50% | — |
| GSM8K | ~64.79 | 50% | — |
| -(CoderPPL) | ~-3.89 | 50% | — |
| LiveCodeBench v6 | ~44.98 | 50% | — |
| MMMU-Pro | ~43.95 | 50% | — |
| MATH | ~40.64 | 50% | — |
| BBH | ~54.69 | 50% | — |